Lab 4

library(tidyverse)

## ── Attaching packages ───────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.2.1     ✓ purrr   0.3.3
## ✓ tibble  2.1.3     ✓ dplyr   0.8.4
## ✓ tidyr   1.0.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.4.0

## ── Conflicts ──────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

###exercise 1

SNPs<- read.table("23andMe_complete.txt", header = TRUE, sep = "\t")
p<-ggplot(SNPs,aes(chromosome))+
  geom_bar(fill = "blue") +
  ggtitle("Total SNPs for each genotype")+
  ylab("SNP count") + 
  xlab("chromosome") 
p

#exercise 2

mycolor<-c("AA"="blue", "AC"="blue", "AG"="blue", "AT"="blue", "CC"="blue", "CG"="blue", "CT"="blue", "GG"="blue", "GT"="blue", "TT"="blue","A"="pink", "C"="pink", "G"="pink", "T"="pink", "D"="orange", "DD"="orange", "DI"="orange","I"="orange","II"="orange","--"="green")
ggplot(SNPs, aes(chromosome, fill = genotype))+
  geom_bar(color = "black")+
  ggtitle("Total SNPs count for each chromosome")+
  ylab("SNP count")+
  xlab("chromosome ")+
  scale_fill_manual(values=c(mycolor)) 

#exercise 3

ppi <- 300
png("Lab3_Exercise5_plot.png", width=6*ppi, height=6*ppi, res=ppi)
ggplot(data=SNPs, aes(chromosome, fill = genotype))+
  geom_bar(position = "dodge")
dev.off()

## quartz_off_screen 
##                 2

#exercise 4

SNPs$chromosome=ordered(SNPs$chromosome, levels=c(seq(1,22),"X","Y","MT"))
ggplot(SNPs, aes(chromosome, fill = genotype))+
  geom_bar(position = "dodge")+ 
  facet_wrap(~genotype, ncol = 2)+
  ggtitle("Genotype for Each Type of Chromosome")+
  ylab("Genotype Count (Thousands)")+
  xlab("Type of Chromosome")

#exercise 5

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

SNPs$chromosome=ordered(SNPs$chromosome,levels=c(seq(1,22),"X","Y","MT"))
p <- ggplot(SNPs, aes(chromosome, fill = genotype))+
    geom_bar(position = "dodge")+ 
    facet_wrap(~genotype, ncol = 2)
p <- ggplotly(p)
p

#exercise 6

library(DT)
chromosome_subset<-subset(SNPs, chromosome=="Y")
datatable(chromosome_subset)

## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html